Automatic choosing of appropriate and the most effective Design Exploration and Predictive Modeling techniques.

What is SmartSelection?

It is well known that the efficiency of Design Exploration and Predictive Modeling solution highly depends on proper technique selection. Tedious tuning of optimization algorithm internal parameters or manual search of the proper predictive modeling technique can consume a lot of time and do not lead to success.

SmartSelection is a technique in tools for Design Exploration and Predictive Modeling in pSeven that automatically chooses the most efficient solution approach for a given type of problem and data. The principle of this technique is that the user should interact with the tool only in terms of the problem description and properties that are important and clear, not in terms of low-level details of the algorithms and techniques that user is unaware of or doesn't care about.


Provide problem description


Use SmartSelection


Get results

Set of hints and options in SmartSelection helps the user to describe the problem and desired solution from his point of view, not from the algorithmic point of view. It hides techniques internal complexity so that the user could concentrate on the engineering problem itself. This opens expert level mathematics for Design Exploration and Predictive Modeling even for non-math experts.

SmartSelection for Design Exploration

Successful Design Exploration process highly depends on many technical aspects and may implement several Design of Experiments and Design Optimization techniques with different set of internal algorithms. That’s why choosing of one static technique for Design Exploration may not lead to the desired result.

SmartSelection uses hints about the problem provided by the user for initial navigation and chooses the algorithm automatically, while its parameters are tuned adaptively during the solution process.

  • Set of options and hints helps the user to describe a problem and desired solution:
    • Types of variables: continuous, discrete, categorical
    • Types of responses: evaluation, minimization, constraint, etc.
    • Function of responses: generic, linear, quadratic, etc.
    • Problem hints: noisy, expensive

In the case of performance degradation of design optimization solution process interrupts and restarts with the next suitable algorithm.

SmartSelection chooses Design Exploration technique based on problem statement

Optimization with SmartSelection vs. open algorithms

Optimization with SmartSelection vs. open algorithms.
NSGA-II, Adaptive Scalarization, SmartSelection – 280 iterations each

SmartSelection for Predictive Modeling

Selection of static technique is often not enough to build an accurate predictive model. The best model type and parameters of predictive modeling technique highly depend on a particular problem and given data. In other words, crucial information from the technical point of view might be not known beforehand.

SmartSelection for Predictive Modeling grants automatic and adaptive technique choosing:

  • Set of hints helps the user to describe problem and desired solution:
    • Hints about the data: dependencies, structure, etc.
    • Desired model properties: exact fit, smooth, etc.
    • Building properties: time, quality, etc.
  • For better approximation quality, different parts of the model can be built using different techniques.

SmartSelection setup for approximation

SmartSelection setup for Predictive Modeling

Different techniques support different options and model building aspects. SmartSelection automatically navigates through all these options and chooses the best techniques for your model:

Options Speed vs. Quality Presets Accuracy Evaluation Exact Fit Linearity Required Tensor Structure Internal Validation Point Weight Smoothing Randomized Training Logarithm of Outputs

  - supported   - supported under certain conditions

Even with default settings SmartSelection builds predictive models of better approximation quality and in shorter time than famous open algorithms, like Scikit-learn, XGBoost and GPy. Learn more >

Accuracy profiles of different predictive modeling techniques

Accuracy profiles of different predictive modeling techniques

Training time profiles of different predicitve modeling techniques

Training time profiles of different predicitve modeling techniques

Interested in the solution?

Click to request a free 30-day demo.

Request demo